Dehydration control method and system, control device and storage medium

Abstract

The invention relates to the technical field of intelligent household appliances, particularly provides a dehydration control method and system, a control device and a storage medium, and aims to solve the technical problem that whether barrel collision is about to occur cannot be predicted in advance in the prior art. In order to achieve the purpose, the dewatering control method comprises the steps that a motion image of a roller of the washing equipment in the dewatering process is obtained; inputting the motion image into a pre-trained identification model, and judging whether the drum is about to collide with the drum; and controlling the washing equipment to execute a preset program according to the judgment result. According to the dehydration control method provided by the invention, the obtained roller motion image is input into the recognition model to predict whether the roller is about to collide with the barrel or not. Compared with the prior art, the method utilizes the image and the model to analyze the motion track of the roller so as to predict whether the roller is about to collide, the detection logic is simple, and the accuracy is high.

Description

Technical Field

[0001] The present invention relates to the technical field of smart home appliances, and specifically provides a dehydration control method, system, control device and storage medium. Background Art

[0002] During the washing process, the washing machine performs a spin spin after washing. If the clothes in the washing tub are unevenly distributed and have a large eccentricity, it is easy for the inner drum to continuously hit the cabinet, causing displacement or even damage to the washing machine and generating a lot of noise. Therefore, it is necessary to monitor the occurrence of the drum collision so as to take corresponding measures.

[0003] Existing washing equipment generally uses vibration switches or related sensors for eccentricity detection to judge or predict barrel-collision events. Among them, the vibration switch or barrel-collision switch generally acts during the barrel-collision process and has certain requirements on the barrel-collision force. Using sensors to detect eccentricity cannot directly reflect whether a barrel-collision has occurred or is about to occur. Therefore, existing washing equipment cannot accurately predict in advance whether the drum is about to collide with the barrel.

[0004] Accordingly, the art needs a new dehydration control method, system, control device and storage medium technical solution to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects, the present invention is proposed to provide a dehydration control method, system, control device and storage medium that solves or at least partially solves the technical problem in the prior art that it is impossible to accurately predict whether a barrel collision is about to occur.

[0006] In a first aspect, the present invention provides a dehydration control method, the method comprising:

[0007] Acquiring a moving image of a drum of a washing device during a dehydration process;

[0008] Inputting the motion image into a pre-trained recognition model to determine whether the drum is about to hit the barrel;

[0009] According to the judgment result, the washing device is controlled to execute a preset program.

[0010] In a technical solution of the above dehydration control method, before the step of “obtaining a motion image of the drum of the washing device during the dehydration process”, the method further includes:

[0011] Obtaining the rotation speed value of the drum of the washing device during the dehydration process;

[0012] Determining whether the rotation speed of the drum is greater than a preset threshold;

[0013] If so, an image acquisition program is started to obtain a moving image of the drum of the washing device during the dehydration process.

[0014] In one technical solution of the above dehydration control method, the “obtaining a motion image of the drum of the washing device during the dehydration process” includes:

[0015] Obtaining the rotation speed value of the drum of the washing device during the dehydration process;

[0016] Determining the image acquisition frequency according to the rotation speed value of the drum;

[0017] The moving image of the drum of the washing device during the dehydration process is acquired at the determined image acquisition frequency.

[0018] In a technical solution of the above dehydration control method, the step of “inputting the motion image into a pre-trained recognition model to determine whether the drum is about to collide with a barrel” includes:

[0019] Preprocessing the motion image to obtain a preprocessed image, wherein the preprocessing operation at least includes grayscale processing;

[0020] The pre-processed image is input into the recognition model to determine whether the drum is about to collide with the barrel.

[0021] In a technical solution of the above dehydration control method, the “controlling the washing device to execute a preset program according to the judgment result” includes:

[0022] If it is determined that the drum will not collide with the tub, controlling the washing device to continue the dehydration process;

[0023] If it is determined that the drum is about to collide with the tub, the washing device is controlled to stop the dehydration program and execute the adjustment program.

[0024] In a technical solution of the above dehydration control method, the method further comprises:

[0025] Monitoring result notification request whether it has been input;

[0026] Based on monitoring that the result notification request is input, the result that the drum of the washing device is about to hit the barrel is sent to the target end.

[0027] In a technical solution of the above dehydration control method, the method further comprises:

[0028] Get the original training image;

[0029] Annotating the original training image to obtain an annotated training image, wherein the annotated result at least includes whether the image hits the barrel, a drum speed value, and a load value;

[0030] Training is performed on the labeled training images to obtain the recognition model

[0031] In a second aspect, the present invention provides a dehydration control system, the system comprising:

[0032] an acquisition module, the acquisition module being configured to acquire a motion image of a drum of a washing device during a dehydration process;

[0033] A judgment module, wherein the analysis module is configured to input the motion image into a pre-trained recognition model to judge whether the drum is about to hit the barrel;

[0034] An execution module is configured to control the washing device to execute a preset program according to the judgment result.

[0035] In a third aspect, a control device is provided, which includes a processor and a storage device, wherein the storage device is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute the dehydration control method described in any one of the technical solutions of the above-mentioned dehydration control method.

[0036] In a fourth aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored in the computer-readable storage medium, wherein the program codes are suitable for being loaded and run by a processor to execute the dehydration control method described in any one of the technical solutions of the above-mentioned dehydration control method.

[0037] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0038] In the technical solution of the present invention, the motion image of the drum of the washing device during the dehydration process is first obtained, and then the motion image is input into a pre-trained recognition model to determine whether the drum is about to hit the barrel, and finally, according to the judgment result, the washing device is controlled to execute a preset program. By inputting the acquired motion image of the drum of the washing device into the recognition model, it is possible to predict whether the barrel is about to hit, and the present invention has simple calculation logic and requires a small amount of data, and can efficiently and accurately predict the barrel hitting event.

[0039] Furthermore, in a technical solution of the present invention, before obtaining the moving image of the drum, the rotation speed value of the drum is first obtained, and then it is determined whether the rotation speed value of the drum is greater than a preset threshold value. Finally, when the rotation speed value of the drum is greater than the preset threshold value, the image acquisition program is started to obtain the moving image of the drum. The present invention sets a preset threshold value, and the image acquisition program is executed only when the rotation speed value of the drum is greater than the preset threshold value. When the rotation speed value of the drum is not greater than the preset threshold value, barrel collision generally does not occur, and energy can be saved by not starting the image acquisition program.

[0040] Furthermore, in a technical solution for implementing the present invention, the frequency of image acquisition is determined according to the rotation speed value of the drum during the dehydration process, and then the moving image of the drum is acquired at the determined frequency. The present invention adjusts the image acquisition frequency in real time according to the real-time rotation speed of the drum, so that the drum can ensure accurate prediction results at high rotation speeds, and can also reduce the amount of calculation at low rotation speeds to reduce energy consumption.

[0041] Furthermore, in a technical solution for implementing the present invention, a preprocessing operation including at least grayscale processing is performed on the acquired motion image, and then it is determined whether the drum is about to hit the barrel based on the preprocessed image. The present invention preprocesses the motion image, wherein the preprocessing operation includes at least grayscale processing, thereby avoiding interference of the color of the load in the barrel on the recognition model and ensuring accurate prediction results.

[0042] Furthermore, in the technical solution of the present invention, when the result notification request is input, the judgment result is sent to the target end when the drum of the washing device is about to hit the drum. The present invention silently executes the preset program when the result request instruction is not detected, and sends the result of the possible drum collision to the target end in time when the result request instruction is detected. Through this setting, the washing device user is given a customized function, and can provide timely reminders to avoid the washing device from hitting the drum. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The disclosure of the present invention will become more easily understood with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In addition, similar numbers in the figures are used to represent similar components, among which:

[0044] Figure 1 It is a schematic flow chart of the main steps of the dehydration control method of the present invention;

[0045] Figure 2 It is a schematic flow chart of the main steps of the present invention for judging whether to start the image acquisition program according to the drum speed value;

[0046] Figure 3It is a schematic flow chart of the main steps of obtaining the drum motion image of the present invention;

[0047] Figure 4 It is a schematic flow chart of the main steps of executing a preset program according to the judgment result of the present invention;

[0048] Figure 5 It is a schematic flow chart of the main steps of the recognition model training of the present invention;

[0049] Figure 6 It is a schematic diagram of the main structural block diagram of the dehydration control system of the present invention.

[0050] Reference numerals list :

[0051] 11: Acquisition module; 12: Analysis module; 13: Execution module. DETAILED DESCRIPTION

[0052] Some embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0053] In the description of the present invention, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, and memories, and may also include software parts, such as program codes, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware, or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store program codes, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and the like. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B", and may include only A, only B, or A and B. The singular terms "one" and "the" may also include plural forms.

[0054] Please see attached picture Figures 1 to 5 ,in, Figure 1 : is a schematic flow chart of the main steps of the dehydration control method of the present invention, which mainly includes steps S1 to S3:

[0055] Step S1, obtaining a moving image of the drum of a washing device during a dehydration process.

[0056] In this embodiment, the motion image of the drum can be obtained by directly capturing images through an image acquisition device, or by intercepting key frames in a video stream captured by the image acquisition device. Each frame of the captured video stream can also be directly used as a motion image. The format and acquisition method of the motion image are not limited herein.

[0057] Step S2: input the motion image into a pre-trained recognition model to determine whether the drum is about to hit the barrel.

[0058] In this embodiment, the recognition model is an artificial intelligence model trained by deep learning technology and mainly using convolutional neural networks, which is used to recognize and understand the content, objects, patterns and features in digital images. The motion image is input into the recognition model to predict whether the drum will hit the barrel in the next 0.5 seconds or 1 second or other time. It should be understood that, in general, the longer the predicted time period, the lower the accuracy of the prediction result. Those skilled in the art can set the appropriate prediction time according to the actual situation, and the present invention is not limited here.

[0059] In another embodiment, the dehydration control method of the present invention further includes: preprocessing the motion image to obtain a preprocessed image, wherein the preprocessing operation includes at least grayscale processing; inputting the preprocessed image into the recognition model to determine whether the drum is about to hit the barrel. In this embodiment, the preprocessing of the acquired image may also include operations such as resizing to ensure the consistency of the input data. By preprocessing the motion image, the present invention avoids the interference of the load color in the barrel on the recognition model and ensures accurate prediction results.

[0060] Step S3: According to the judgment result, the washing equipment is controlled to execute a preset program.

[0061] In this embodiment, a preset program is executed according to the judgment result output by the recognition model, wherein the preset program may include continuing the dehydration program, continuing the dehydration program and increasing the power, continuing the dehydration program and reducing the power, pausing the dehydration power and executing the clothing redistribution program, etc. These preset programs should correspond to the judgment result output by the recognition model. Those skilled in the art can set corresponding programs according to different judgment results, and the present invention is not limited here.

[0062] In another embodiment, the dehydration control method of the present invention further includes: monitoring whether a result notification request is input; based on monitoring that the result notification request is input, sending the result that the drum of the washing device is about to hit the barrel to the target end. The "monitoring result notification request" in this embodiment is an information subscription request input by the user, indicating that the user intends to obtain information notifications about the impending barrel collision in a timely manner. Upon receiving the request, if the recognition model predicts that the drum is about to hit the barrel, the washing device will immediately send the information to the target end, wherein the target end can be an information display device of the washing device or a portable device of the user. Through this setting, the user of the washing device is given a customized function, and can provide timely reminders to avoid the washing device from hitting the barrel.

[0063] Based on the above steps S1 to S3, it can be known that in the implementation of the technical solution of the present invention, the motion image of the drum of the washing device during the dehydration process is first obtained, and then the motion image is input into a pre-trained recognition model to determine whether the drum is about to hit the barrel, and finally, according to the judgment result, the washing device is controlled to execute a preset program. By inputting the acquired motion image of the drum of the washing device into the recognition model, it is possible to predict whether a barrel collision is about to occur, and the calculation logic of the present invention is simple and the amount of data required is small, and barrel collision events can be predicted efficiently and accurately.

[0064] Combination Figure 1 and Figure 2 ,in, Figure 2 It is a schematic flow chart of the main steps of the present invention for judging whether to start the image acquisition program according to the drum speed value. The dehydration control method of the present invention also includes steps S01 to S03:

[0065] Step S01, obtaining the rotation speed value of the drum of the washing device during the dehydration process.

[0066] In this embodiment, the obtained rotation speed value of the drum may be a calibration value corresponding to the dehydration speed selected by the user, or may be an actual value of the rotation speed of the drum during the dehydration process. It should be understood that if a person skilled in the art sets the obtained rotation speed value of the drum as an actual value, a device capable of obtaining the actual rotation speed of the drum in real time needs to be provided in the washing device to obtain a more accurate value. If a person skilled in the art sets the obtained rotation speed value of the drum as a calibration value, a reasonable error calculation rule may be added to obtain an accurate value while saving energy.

[0067] Step S02: determine whether the rotation speed of the drum is greater than a preset threshold.

[0068] In this embodiment, the preset threshold value can be a value set by technicians in this field when producing the washing device, or a value set by the user of the washing device during actual use, or a value automatically adjusted by the washing device based on past usage records, or a value automatically set by the washing device based on the load in the drum. The specific setting method is not limited here.

[0069] Step S03: If yes, start the image acquisition program to obtain the moving image of the drum of the washing device during the dehydration process.

[0070] In this embodiment, if the rotation speed of the drum reaches the preset threshold, it proves that at this rotation speed value, the drum has the possibility of colliding with the barrel. The image acquisition device can be in a normally open state, or it can be in an open and closed state controlled by the processor. For example: the image acquisition device is in a normally open state, and it continuously obtains the motion image of the drum and saves the obtained image to the cache area. When the rotation speed of the drum reaches the preset threshold, the processor obtains the image from the cache area; the image acquisition device is in an open and closed state controlled by the processor. Only when the rotation speed of the drum reaches the preset threshold, the processor sends a signal to turn on the image acquisition device, and the image processor starts to capture images after receiving the signal. Those skilled in the art can set a reasonable working mode for the image acquisition device according to actual conditions, and the present invention is not limited here.

[0071] Based on the above steps S01 to S03, it can be known that in a technical solution of the present invention, before obtaining the moving image of the drum, the rotation speed value of the drum is first obtained, and then it is determined whether the rotation speed value of the drum is greater than a preset threshold value. Finally, when the rotation speed value of the drum is greater than the preset threshold value, the image acquisition program is started to obtain the moving image of the drum. The present invention sets a preset threshold value, and the image acquisition program is executed only when the rotation speed value of the drum is greater than the preset threshold value. When the rotation speed value of the drum is not greater than the preset threshold value, barrel collision generally does not occur, and energy can be saved by not starting the image acquisition program.

[0072] Combination Figure 1 and Figure 3 ,in, Figure 3 1 is a schematic flow chart of the main steps of obtaining the drum motion image of the present invention. The dehydration control method of the present invention also includes steps S11 to S13:

[0073] Step S11, obtaining the rotation speed value of the drum of the washing device during the dehydration process.

[0074] In this embodiment, the obtained rotation speed value of the drum may be a calibration value corresponding to the dehydration speed selected by the user, or may be an actual value of the rotation speed of the drum during the dehydration process. It should be understood that if a person skilled in the art sets the obtained rotation speed value of the drum as an actual value, a device capable of obtaining the actual rotation speed of the drum in real time needs to be provided in the washing device to obtain a more accurate value. If a person skilled in the art sets the obtained rotation speed value of the drum as a calibration value, a reasonable error calculation rule may be added to obtain an accurate value while saving energy.

[0075] Step S12: determining the image acquisition frequency according to the rotation speed value of the drum.

[0076] In this embodiment, when the calibration value is used as the dehydration speed of the drum, the image acquisition frequency is a fixed value corresponding to the calibration value, and when the actual value is used as the dehydration speed of the drum, the image acquisition frequency is a non-fixed value corresponding to the real-time actual speed of the drum. Generally, a higher speed corresponds to a higher image acquisition frequency to obtain a more accurate motion image.

[0077] Step S13: acquiring a moving image of the drum of the washing device during the dehydration process at the determined image acquisition frequency.

[0078] In this embodiment, the image acquisition device can be in a normally open state or in an open and closed state controlled by a processor. For example, the image acquisition device is in a normally open state, and it continuously acquires the moving image of the drum and saves the acquired image to a cache area. When the rotation speed of the drum reaches the preset threshold, the processor acquires the image from the cache area. The image acquisition device is in an open and closed state controlled by a processor. Only when the rotation speed of the drum reaches the preset threshold, the processor issues a signal to open the image acquisition device, and the image processor starts to capture images after receiving the signal. Those skilled in the art can set a reasonable working mode for the image acquisition device according to actual conditions, and the present invention is not limited here.

[0079] Based on the above steps S11 to S13, it can be known that in a technical solution of the present invention, the frequency of image acquisition is determined according to the rotation speed value of the drum during the dehydration process, and then the moving image of the drum is acquired at the determined frequency. The present invention adjusts the image acquisition frequency in real time according to the real-time rotation speed of the drum, so that the drum can ensure accurate prediction results at high rotation speeds, and can also reduce the amount of calculation at low rotation speeds to reduce energy consumption.

[0080] Combination Figure 1 and Figure 4 ,in, Figure 4 1 is a schematic flow chart of the main steps of executing a preset program according to the judgment result of the present invention. The dehydration control method of the present invention also includes steps S31 and S32:

[0081] Step S31: If it is determined that the drum will not collide with the tub, the washing device is controlled to continue the dehydration process.

[0082] In this embodiment, the dehydration program to be continued does not mean that the currently selected dehydration program must be continued, and may also include a dehydration program with higher power or a dehydration program with lower power, all of which belong to the dehydration program mentioned here. Those skilled in the art can analyze the motion image of the drum through the recognition model to obtain the motion trajectory data of the drum, and set the corresponding dehydration program according to the data, and the present invention is not limited here.

[0083] Step S32: If it is determined that the drum is about to collide with the tub, the washing device is controlled to stop the dehydration process and execute the adjustment process.

[0084] In this embodiment, when the recognition model predicts that a barrel collision is about to occur, the processor outputs a signal to stop the dehydration program, and after receiving the signal, the dehydration device of the washing device controls the drum to stop dehydration and executes the adjustment program. The adjustment program can be a program pre-set by a person skilled in the art, for example, it can be a signal to output redistribution to control the motor of the washing device to perform a clothes redistribution operation, or it can be an emergency brake signal to control the drum to perform an emergency brake, or it can be a program set by the user, such as stopping the dehydration program and outputting a prompt message, and the present invention is not limited here.

[0085] Combination Figure 1 and Figure 5 ,in, Figure 5 4 is a schematic flow chart of the main steps of the recognition model training of the present invention. The dehydration control method of the present invention also includes steps S41 to S43:

[0086] Step S41, obtaining an original training image.

[0087] In this embodiment, the original training images refer to a large number of images acquired in advance for training. Generally speaking, these original images come from motion images of drums of different devices under different working conditions. In some embodiments, preprocessing operations may also be performed on these original images, including but not limited to resizing, standardization, and enhancement, to ensure the consistency and quality of input data.

[0088] Step S42: annotate the original training image to obtain an annotated training image.

[0089] In this embodiment, labeling the original image is to label the original image, and the label includes at least three dimensions: "hitting the barrel or not hitting the barrel", "drum speed value" and "load value".

[0090] Step S43: training the labeled training images to obtain a recognition model.

[0091] In this embodiment, specific training parameters such as weight values, loss functions, learning rates, batch sizes, etc. can be appropriately adjusted by those skilled in the art according to actual conditions, and the present invention is not limited thereto.

[0092] So far, the dehydration control method of the present invention has been described. Although the various steps in the above embodiment are described in a specific order, those skilled in the art can understand that in order to achieve the effect of the present invention, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

[0093] Furthermore, the present invention also provides a dehydration control system.

[0094] See attached Figure 6 , Figure 6 FIG. 1 is a main structural block diagram of a dehydration control system according to an embodiment of the present invention. Figure 6 As shown, the dehydration control system in the embodiment of the present invention mainly includes an acquisition module 11, an analysis module 12 and an execution module 13. In some embodiments, one or more of the acquisition module 11, the analysis module 12 and the execution module 13 can be combined into one module. In some embodiments, the acquisition module 11 can be configured to acquire a motion image of the drum of the washing device during the dehydration process. The analysis module 12 can be configured to input the motion image into a pre-trained recognition model to determine whether the drum is about to hit the barrel. The execution module 13 can be configured to control the washing device to execute a preset program based on the judgment result.

[0095] The dehydration control system is used to implement Figure 1 The dehydration control method embodiment shown in the figure has similar technical principles, technical problems solved and technical effects produced. Technicians in this technical field can clearly understand that for the convenience and conciseness of description, the specific working process and related instructions of the dehydration control system can refer to the contents described in the embodiment of the dehydration control method, which will not be repeated here.

[0096] It is understood by those skilled in the art that the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0097] Furthermore, the present invention also provides a control device. In an embodiment of a control device according to the present invention, the control device includes a processor and a storage device, the storage device can be configured to store a program for executing the dehydration control method of the above method embodiment, and the processor can be configured to execute the program in the storage device, which includes but is not limited to the program for executing the dehydration control method of the above method embodiment. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The control device can be a control device device formed by various electronic devices.

[0098] Furthermore, the present invention also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium can be configured to store a program for executing the dehydration control method of the above method embodiment, and the program can be loaded and run by the processor to implement the above dehydration control method. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.

[0099] Further, it should be understood that since the setting of each module is only for illustrating the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only schematic.

[0100] Those skilled in the art will appreciate that the modules in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principle of the present invention, and therefore, the technical solutions after splitting or merging will fall within the protection scope of the present invention.

[0101] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A dehydration control method, characterized in that: The method comprises: Acquiring a moving image of a drum of a washing device during a dehydration process; Inputting the motion image into a pre-trained recognition model to determine whether the drum is about to hit the barrel; According to the judgment result, the washing device is controlled to execute a preset program.

2. The dehydration control method according to claim 1, characterized in that: Before the step of "obtaining a moving image of the drum of the washing device during the dehydration process", the method further includes: Obtaining the rotation speed value of the drum of the washing device during the dehydration process; Determining whether the rotation speed of the drum is greater than a preset threshold; If so, an image acquisition program is started to obtain a moving image of the drum of the washing device during the dehydration process.

3. The dehydration control method according to claim 1, characterized in that: The “obtaining a moving image of the drum of the washing device during the dehydration process” includes: Obtaining the rotation speed value of the drum of the washing device during the dehydration process; Determining the image acquisition frequency according to the rotation speed value of the drum; The moving image of the drum of the washing device during the dehydration process is acquired at the determined image acquisition frequency.

4. The dehydration control method according to claim 1, characterized in that: The "inputting the motion image into a pre-trained recognition model to determine whether the drum is about to hit the barrel" includes: Preprocessing the motion image to obtain a preprocessed image, wherein the preprocessing operation at least includes grayscale processing; The pre-processed image is input into the recognition model to determine whether the drum is about to collide with the barrel.

5. The dehydration control method according to claim 1, characterized in that: The “controlling the washing device to execute a preset program according to the judgment result” includes: If it is determined that the drum will not collide with the tub, controlling the washing device to continue the dehydration process; If it is determined that the drum is about to collide with the tub, the washing device is controlled to stop the dehydration program and execute the adjustment program.

6. The dehydration control method according to claim 1, characterized in that: The method further comprises: Monitoring result notification request whether it has been input; Based on monitoring that the result notification request is input, the result that the drum of the washing device is about to hit the barrel is sent to the target end.

7. The dehydration control method according to claim 1, characterized in that: The training method of the recognition model includes: Get the original training image; Annotating the original training image to obtain an annotated training image, wherein the annotated result at least includes whether the image hits the barrel, a drum speed value, and a load value; Training is performed on the labeled training images to obtain the recognition model.

8. A dehydration control system, characterized in that: The system comprises: an acquisition module, the acquisition module being configured to acquire a motion image of a drum of a washing device during a dehydration process; A judgment module, wherein the analysis module is configured to input the motion image into a pre-trained recognition model to judge whether the drum is about to hit the barrel; An execution module is configured to control the washing device to execute a preset program according to the judgment result.

9. A control device, comprising a processor and a storage device, wherein the storage device is suitable for storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by the processor to execute the dehydration control method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the dehydration control method according to any one of claims 1 to 7.

Images